Joint modeling of multiple time series via the beta process with application to motion capture segmentation
This work addresses the challenge of unsupervised segmentation for motion capture data, which is incremental as it builds on existing Bayesian nonparametric methods.
The authors tackled the problem of jointly modeling multiple related time series by proposing a Bayesian nonparametric approach that discovers a latent set of shared dynamical behaviors and segments each series accordingly, demonstrating promising results on unsupervised segmentation of human motion capture data.
We propose a Bayesian nonparametric approach to the problem of jointly modeling multiple related time series. Our model discovers a latent set of dynamical behaviors shared among the sequences, and segments each time series into regions defined by a subset of these behaviors. Using a beta process prior, the size of the behavior set and the sharing pattern are both inferred from data. We develop Markov chain Monte Carlo (MCMC) methods based on the Indian buffet process representation of the predictive distribution of the beta process. Our MCMC inference algorithm efficiently adds and removes behaviors via novel split-merge moves as well as data-driven birth and death proposals, avoiding the need to consider a truncated model. We demonstrate promising results on unsupervised segmentation of human motion capture data.